Microstructure evolution of lithium-ion battery electrodes at different states of charge: Deep learning-based segmentation

TY - JOUR

T1 - Microstructure evolution of lithium-ion battery electrodes at different states of charge

T2 - Deep learning-based segmentation

AU - Yang, Yazheng

AU - Li, Ning

AU - Wang, Bin

AU - Li, Na

AU - Gao, Kai

AU - Liang, Yudong

AU - Wei, Yimin

AU - Yang, Le

AU - Song, Wei Li

AU - Chen, Haosen

N1 - Publisher Copyright: © 2022 The Author(s)

PY - 2022/3

Y1 - 2022/3

N2 - The evolution of the microstructure of a battery electrode is closely related to battery performance. Characterization and visualization of the evolution of the microstructure is essential for optimization of manufactured electrodes. The validity of the battery structure representation affects the accuracy of the extracted microstructure parameters. In this study, a mini-cylindrical battery is designed to allow microstructure parameters to be obtained at different states of charge, bearing in mind the influence of the real battery structure. An argon-ion cross-section polisher is used to obtain a large area of the electrode for observation. In addition, an image segmentation method based on a modified U-Net neural network is developed to enhance the quality of the extracted microstructure. The relationship between porosity and thickness at different states of electrode charge is presented through experiments and deep learning of images. This method provides new insight into the evolution of electrode microstructure and can potentially guide the manufacturing of lithium-ion batteries.

AB - The evolution of the microstructure of a battery electrode is closely related to battery performance. Characterization and visualization of the evolution of the microstructure is essential for optimization of manufactured electrodes. The validity of the battery structure representation affects the accuracy of the extracted microstructure parameters. In this study, a mini-cylindrical battery is designed to allow microstructure parameters to be obtained at different states of charge, bearing in mind the influence of the real battery structure. An argon-ion cross-section polisher is used to obtain a large area of the electrode for observation. In addition, an image segmentation method based on a modified U-Net neural network is developed to enhance the quality of the extracted microstructure. The relationship between porosity and thickness at different states of electrode charge is presented through experiments and deep learning of images. This method provides new insight into the evolution of electrode microstructure and can potentially guide the manufacturing of lithium-ion batteries.

KW - Deep learning

KW - Microstructure evolution

KW - Mini-cylindrical battery

KW - Real structure

KW - Thickness and porosity

UR - https://www.scopus.com/pages/publications/85123835150

U2 - 10.1016/j.elecom.2022.107224

DO - 10.1016/j.elecom.2022.107224

M3 - Article

AN - SCOPUS:85123835150

SN - 1388-2481

VL - 136

JO - Electrochemistry Communications

JF - Electrochemistry Communications

M1 - 107224

ER -